View in EDS HTML Full Text PDF Full Text

Electricity Theft Detection from Electricity and Gas Measurements Using Machine Learning.

Saved in:
Bibliographic Details
Title: Electricity Theft Detection from Electricity and Gas Measurements Using Machine Learning.
Authors: Alfaverh, Fayiz1 (AUTHOR), Gan, Hock1,2 (AUTHOR), Miroshnyk, Volodymyr2,3 (AUTHOR), Bin Saeed, Zaid3,4 (AUTHOR), Blinov, Ihor2,4 (AUTHOR), Shymaniuk, Pavlo2 (AUTHOR), Tarassodi, Pouya3 (AUTHOR), Mporas, Iosif1 (AUTHOR)
Source: Energies (19961073). May2026, Vol. 19 Issue 9, p2045. 29p.
Subject Terms: *Machine learning, *Decision trees, *Smart power grids, *Feature selection
Abstract: Electricity theft is a critical source of non-technical losses in modern power systems, causing substantial financial and operational challenges for utilities. Traditional detection methods, such as manual inspections, are inadequate to detect advanced theft techniques, including meter tampering and cyberattacks on smart grids. This study introduces a machine learning-based framework for electricity theft detection using the TDD2022 dataset (derived from OEDI) and evaluates multiple algorithms—Random Forest, Decision Tree, XGBoost, LightGBM, CatBoost, Extra Trees, and Logistic Regression. To address class imbalance, SMOTE is applied, while feature selection leverages LASSO and ReliefF. Experiments compare electricity-only data with multi-utility inputs (electricity and gas) under balanced and imbalanced conditions. Results show that tree-based ensembles, particularly Extra Trees combined with SMOTE and ReliefF, achieve superior performance (accuracy > 95 % , AUC ≈ 0.99 ). Consumer-specific models outperform global models, with commercial classes yielding near-perfect detection, while residential profiles remain challenging. The findings highlight the importance of tailored modeling and feature selection for scalable, accurate theft detection in smart grid environments. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 193715941
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Electricity Theft Detection from Electricity and Gas Measurements Using Machine Learning.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Alfaverh%2C+Fayiz%22">Alfaverh, Fayiz</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gan%2C+Hock%22">Gan, Hock</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Miroshnyk%2C+Volodymyr%22">Miroshnyk, Volodymyr</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Bin+Saeed%2C+Zaid%22">Bin Saeed, Zaid</searchLink><relatesTo>3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Blinov%2C+Ihor%22">Blinov, Ihor</searchLink><relatesTo>2,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Shymaniuk%2C+Pavlo%22">Shymaniuk, Pavlo</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Tarassodi%2C+Pouya%22">Tarassodi, Pouya</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Mporas%2C+Iosif%22">Mporas, Iosif</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Energies+%2819961073%29%22">Energies (19961073)</searchLink>. May2026, Vol. 19 Issue 9, p2045. 29p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Decision+trees%22">Decision trees</searchLink><br />*<searchLink fieldCode="DE" term="%22Smart+power+grids%22">Smart power grids</searchLink><br />*<searchLink fieldCode="DE" term="%22Feature+selection%22">Feature selection</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Electricity theft is a critical source of non-technical losses in modern power systems, causing substantial financial and operational challenges for utilities. Traditional detection methods, such as manual inspections, are inadequate to detect advanced theft techniques, including meter tampering and cyberattacks on smart grids. This study introduces a machine learning-based framework for electricity theft detection using the TDD2022 dataset (derived from OEDI) and evaluates multiple algorithms—Random Forest, Decision Tree, XGBoost, LightGBM, CatBoost, Extra Trees, and Logistic Regression. To address class imbalance, SMOTE is applied, while feature selection leverages LASSO and ReliefF. Experiments compare electricity-only data with multi-utility inputs (electricity and gas) under balanced and imbalanced conditions. Results show that tree-based ensembles, particularly Extra Trees combined with SMOTE and ReliefF, achieve superior performance (accuracy > 95 % , AUC ≈ 0.99 ). Consumer-specific models outperform global models, with commercial classes yielding near-perfect detection, while residential profiles remain challenging. The findings highlight the importance of tailored modeling and feature selection for scalable, accurate theft detection in smart grid environments. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=193715941
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/en19092045
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 29
        StartPage: 2045
    Subjects:
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Decision trees
        Type: general
      – SubjectFull: Smart power grids
        Type: general
      – SubjectFull: Feature selection
        Type: general
    Titles:
      – TitleFull: Electricity Theft Detection from Electricity and Gas Measurements Using Machine Learning.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Alfaverh, Fayiz
      – PersonEntity:
          Name:
            NameFull: Gan, Hock
      – PersonEntity:
          Name:
            NameFull: Miroshnyk, Volodymyr
      – PersonEntity:
          Name:
            NameFull: Bin Saeed, Zaid
      – PersonEntity:
          Name:
            NameFull: Blinov, Ihor
      – PersonEntity:
          Name:
            NameFull: Shymaniuk, Pavlo
      – PersonEntity:
          Name:
            NameFull: Tarassodi, Pouya
      – PersonEntity:
          Name:
            NameFull: Mporas, Iosif
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 19961073
          Numbering:
            – Type: volume
              Value: 19
            – Type: issue
              Value: 9
          Titles:
            – TitleFull: Energies (19961073)
              Type: main
ResultId 1